Triple

T3648970
Position Surface form Disambiguated ID Type / Status
Subject John Francis Daley E77371 entity
Predicate notableWork P4 FINISHED
Object Bones E328563 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Bones | Statement: [John Francis Daley, notableWork, Bones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bones
Context triple: [John Francis Daley, notableWork, Bones]
  • A. Bones
    Bones is the nickname of Bones McKinney, a notable American basketball player and coach from the mid-20th century.
  • B. Bones chosen
    Bones is a 2001 supernatural horror film starring Snoop Dogg as a murdered man who returns from the dead to exact revenge.
  • C. Bones
    "Bones" is the official theme song used for WWE's WrestleMania 29 event.
  • D. CSI: Crime Scene Investigation
    CSI: Crime Scene Investigation is a popular American procedural drama series that follows forensic investigators as they use scientific techniques to solve crimes.
  • E. Rizzoli & Isles
    Rizzoli & Isles is an American crime drama television series that follows a Boston homicide detective and a medical examiner as they solve complex murder cases.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ad85de1b988190a45f8dbfebc806fc completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc38c22548190a271a69fb832a5a8 completed March 8, 2026, 6:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69b44f3c85348190b1d16179294f7f09 completed March 13, 2026, 5:54 p.m.
Created at: March 8, 2026, 3:24 p.m.